AI-generated reporting significantly reduces radiologists' reading times and increases report acceptability over time.
Key Details
- 1Study published in JACR evaluated AI-generated reports for chest X-rays.
- 2Researchers used Kakao Brain’s KARA-CXR model on a dataset of 756 radiographs.
- 3Five radiologists generated preliminary AI reports; two assessed acceptability and need for revisions.
- 4Human approval rates of AI-generated reports increased, indicating growing trust.
- 5Experts call for further study into improving preliminary AI reports and their impact on diagnostics.
Why It Matters
Streamlining reporting with AI could improve radiologist efficiency and address workforce pressures. Increased acceptability suggests AI integration is advancing, but accuracy and clinical impact remain focus areas for future research.
Source
Radiology Business
Related News
•AuntMinnie
Radiologists Struggle to Spot AI-Generated Radiology Images
Radiologists correctly identify AI-generated images 75% of the time, with CT and MRI images being particularly challenging to spot.
•AuntMinnie
Radiology Leads FDA AI Device Approvals Over Three Decades
Radiology accounts for 76% of all FDA-cleared AI/ML-enabled medical devices as of the end of 2025.
•Radiology Business
Automation Bias: How AI Can Compromise Radiologist Accuracy
AI decision support can induce automation bias, leading radiologists to accept incorrect interpretations and potentially reduce their diagnostic accuracy.